Search for: All records

Do common assumptions about the way that crowd workers make mistakes in microtask (labeling) applications manifest in real crowdsourcing data? Prior work only addresses this question indirectly. Instead, it primarily focuses on designing new label aggregation algorithms, seeming to imply that better performance justifies any additional assumptions. However, empirical evidence in past instances has raised significant challenges to common assumptions. We continue this line of work, using crowdsourcing data itself as directly as possible to interrogate several basic assumptions about workers and tasks. We find strong evidence that the assumption that workers respond correctly to each task with a constant probability, which is common in theoretical work, is implausible in real data. We also illustrate how heterogeneity among tasks and workers can take different forms, which have different implications for the design and evaluation of label aggregation algorithms. 

Do common assumptions about the way that crowd workers make mistakes in microtask (labeling) applications manifest in real crowdsourcing data? Prior work only addresses this question indirectly. Instead, it primarily focuses on designing new label aggregation algorithms, seeming to imply that better performance justifies any additional assumptions. However, empirical evidence in past instances has raised significant challenges to common assumptions. We continue this line of work, using crowdsourcing data itself as directly as possible to interrogate several basic assumptions about workers and tasks. We find strong evidence that the assumption that workers respond correctly to each task with a constant probability, which is common in theoretical work, is implausible in real data. We also illustrate how heterogeneity among tasks and workers can take different forms, which have different implications for the design and evaluation of label aggregation algorithms. 

We propose measurement integrity, a property related to ex post reward fairness, as a novel desideratum for peer prediction mechanisms in many natural applications. Like robustness against strategic reporting, the property that has been the primary focus of the peer prediction literature, measurement integrity is an important consideration for understanding the practical performance of peer prediction mechanisms. We perform computational experiments, both with an agent-based model and with real data, to empirically evaluate peer prediction mechanisms according to both of these important properties. Our evaluations simulate the application of peer prediction mechanisms to peer assessment---a setting in which ex post fairness concerns are particularly salient. We find that peer prediction mechanisms, as proposed in the literature, largely fail to demonstrate significant measurement integrity in our experiments. We also find that theoretical properties concerning robustness against strategic reporting are somewhat noisy predictors of empirical performance. Further, there is an apparent trade-off between our two dimensions of analysis. The best-performing mechanisms in terms of measurement integrity are highly susceptible to strategic reporting. Ultimately, however, we show that supplementing mechanisms with realistic parametric statistical models can, in some cases, improve performance along both dimensions of our analysis and result in mechanisms that strike the best balance between them.